Skill UI

A comprehensive multi-phase tool designed to rigorously check the novelty of proposed research methods or technical ideas against current academic literature. It systematically extracts core claims, performs multi-source literature searches (including arXiv, major conferences, and web databases), and uses advanced cross-model verification to generate a structured, actionable Novelty Report, advising on the unique contribution and research positioning.

This skill provides a multi-round, high-depth critical review of academic research projects, simulating the rigorous feedback process of top-tier conferences (e.g., NeurIPS, ICML). It guides the user through identifying logical gaps, suggesting missing experiments, and refining the core narrative claims to maximize acceptance chances.

This gate systematically evaluates experimental outcomes against intended research claims. It collects metrics from various sources (W&B, logs, etc.) and uses an objective judgment model to determine if the data supports, partially supports, or fails to support the hypothesis. It provides specific evidence gaps and suggests concrete next steps, guiding the research workflow before writing papers or finalizing designs.

This tool functions as a persistent, structured knowledge base for the entire research lifecycle. It accumulates and maps all core research entities—including published papers, generated ideas, experiments, and testable claims—along with their complex relationships (e.g., contradiction, support, inspiration). Inspired by LLM Wiki patterns, it ensures that knowledge is compounded and perpetually queryable, moving beyond single-use literature reviews.